Medical Image Indexing using Attributed Relational Graphs and Rectangular Trees
Main Article Content
Abstract
Given a collection of medical images (like CT scans), we derive appropriate representations of their content and organize the images
together with representations in a multi-dimensional data structure so that we can search efficiently for images similar to an example image.
Image content is represented by Attributed Relational Graphs (ARGs) holding features of objects and relationships between objects. Our
proposed image indexing and similarity search methods rely on the assumption that a fixed number of “labelled†or “expected†objects (e.g.,
“heartâ€, “lungs†etc) are common in all images of a given application domain in addition to a variable number of “unexpected†or “unlabeledâ€
objects (e.g., “tumorâ€, “hematoma†etc). Our method can answer queries by example such as “find all X-rays that are similar to Smith’s X-ray.â€
The stored images are mapped to points in a multi-dimensional space and are indexed using state-of-the-art database methods (R-trees). The
proposed method has several desirable properties: (a) Database search is approximate so that all images up to a pre-specified degree of similarity
(tolerance) are retrieved; (b) it has no “false dismissals†(i.e. all images qualifying query selection criteria are retrieved) and (c) it is much faster
than sequential scanning for searching in the main memory and on the disk (i.e. by up to an order of magnitude); thus, scaling-up well for larger
databases.
Â
Keywords: Indexing, Similarity Searching, Medical Images, R-tree, Attributed Relational Graphs
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.